Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Sample reconstruction with deep autoencoder for one sample per person face recognition

  • Author(s): Yan Zhang 1, 2  and  Hua Peng 1
    • View affiliations
  • Source: Volume 11, Issue 6, September 2017, p. 471 – 478
    DOI:  10.1049/iet-cvi.2016.0322 , Print ISSN 1751-9632, Online ISSN 1751-9640
© The Institution of Engineering and Technology
Received 13/09/2016, Accepted 01/05/2017, Revised 29/03/2017, Published 03/05/2017

One sample per person (OSPP) face recognition is a challenging problem in face recognition community. Lack of samples is the main reason for the failure of most algorithms in OSPP. In this study, the authors propose a new algorithm to generalise intra-class variations of multi-sample subjects to single-sample subjects by deep autoencoder and reconstruct new samples. In the proposed algorithm, a generalised deep autoencoder is first trained with all images in the gallery, then a class-specific deep autoencoder (CDA) is fine-tuned for each single-sample subject with its single sample. Samples of the multi-sample subject, which is most like the single-sample subject, are input to the corresponding CDA to reconstruct new samples. For classification, minimum L2 distance, principle component analysis, sparse represented-based classifier and softmax regression are used. Experiments on the Extended Yale Face Database B, AR database and CMU PIE database are provided to show the validity of the proposed algorithm.

Inspec keywords: image representation; principal component analysis; regression analysis; image classification; image coding; face recognition; image reconstruction

Other keywords: OSPP face recognition; one sample per person face recognition; multisample subject to single-sample subject intraclass variations; class-specific deep autoencoder; principle component analysis; sparse represented-based classifier; CDA; minimum L2 distance; sample reconstruction; softmax regression; CMU database; AR database; image classification; extended Yale face database B

Subjects: Image recognition; Image and video coding; Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics

References

    1. 1)
      • 27. Gross, R., Matthews, I., Cohn, J.F., et al: ‘Multi-PIE’. Proc. of the Eighth IEEE Int. Conf. on Automatic Face and Gesture Recognition, 2008.
    2. 2)
      • 15. Hinton, G.E., Salakhutdinov, R.R.: ‘Reducing the dimensionality of data with neural networks’, Science, 2006, 313, (5786), pp. 504–507.
    3. 3)
      • 30. Deng, W., Hu, J., Guo, J., et al: ‘Robust, accurate and efficient face recognition from a single training image: a uniform pursuit approach’, Pattern Recognit., 2010, 43, (5), pp. 1748–1762.
    4. 4)
      • 5. Roweis, S.T., Saul, L.K.: ‘Nonlinear dimensionality reduction by locally linear embedding’, Science, 2000, 290, (5500), pp. 2323–2326.
    5. 5)
      • 19. Ding, Z., Shao, M., Fu, Y.: ‘Deep Robust Encoder through locality preserving low-rank dictionary’. The 14th European Conf. on Computer Vision, The Netherlands, 2016.
    6. 6)
      • 11. Deng, W., Hu, J., Guo, J.: ‘In defense of sparsity based face recognition’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Oregon, Portland, 2013, pp. 399–406.
    7. 7)
      • 2. Etemad, K., Chellappa, R.: ‘Discriminant analysis for recognition of human face images’, J. Opt. Soc. Am. A, 1997, 14, (8), pp. 1724–1733.
    8. 8)
      • 22. Gao, S., Zhang, Y., Jia, K., et al: ‘Single sample face recognition via learning deep supervised autoencoders’, IEEE Trans. Inf. Forensics Sec., 2015, 10, (10), pp. 2108–2118.
    9. 9)
      • 17. Lv, Y., Duan, Y., Kang, W., et al: ‘Traffic flow prediction with big data: a deep learning approach’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (2), pp. 865–873.
    10. 10)
      • 23. Turk, M., Pentland, A.: ‘Eigenfaces for recognition’, J. Cogn. Neurosci., 1991, 3, (1), pp. 71–86.
    11. 11)
      • 12. Deng, W., Hua, J., Zhou, X., et al: ‘Equidistant prototypes embedding for single sample based face recognition with generic learning and incremental learning’, Pattern Recognit., 2014, 47, (12), pp. 3738–3749.
    12. 12)
      • 28. Hinton, G.E.: ‘A practical guide to training restricted boltzmann machines’. UTML TR 2010–003, University of Toronto, 2010.
    13. 13)
      • 34. Liu, C., Wechsler, H.: ‘Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition’, IEEE Trans. Image Process., 2002, 11, (4), pp. 467–476.
    14. 14)
      • 8. Deng, W., Hu, J., Guo, J.: ‘Extended SRC: undersampled face recognition via intraclass variant dictionary’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (9), pp. 1864–1870.
    15. 15)
      • 24. Juan, I., Jesus, C.S., Tulay, A., et al: ‘Estimates of constrained multi-class a posteriori probabilities in time series problems with neural networks’. Int. Symp. on Neural Networks, Wahington, DC, 1999, pp. 1560–1561.
    16. 16)
      • 14. Ding, Z., Fu, Y.: ‘Robust multi-view subspace learning through dual low-rank decompositions’. The Thirtieth AAAI Conf. on Artificial Intelligence, USA, 2016.
    17. 17)
      • 6. Wright, J., Yang, A.Y., Ganesh, A., et al: ‘Robust face recognition via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (2), pp. 210–227.
    18. 18)
      • 7. Naseem, I., Togneri, R., Bennamoun, M.: ‘Linear regression for face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 33, (11), pp. 2016–2112.
    19. 19)
      • 18. Lange, S., Riedmiller, M.: ‘Deep auto-encoder neural networks in reinforcement learning’. The 2010 Int. Joint Conf. on Neural Networks (IJCNN), Barcelona, 2010, pp. 1–8.
    20. 20)
      • 33. Ahonen, T., Hadid, A., Pietikäinen, M.: ‘Face recognition with local binary patterns’. European Conf. on Computer Vision, 2004.
    21. 21)
      • 16. Bengio, Y., Courville, A., Vincent, P.: ‘Representation learning: a review and new perspectives’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (8), pp. 1798–1828.
    22. 22)
      • 20. Erhan, D., Bengio, Y., Courville, A., et al: ‘Why does unsupervised pre-training help deep learning?’, J. Mach. Learn. Res., 2010, 11, (3), pp. 625–660.
    23. 23)
      • 25. Georghiades, A., Belhumeur, P., Kriegman, D.: ‘From few to many: illumination cone models for face recognition under variable lighting and pose’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (6), pp. 643–660.
    24. 24)
      • 35. Peng, X., Feris, R.S., Wang, X., et al: ‘Metaxas a recurrent encoder–decoder network for sequential face alignment’. European Conf. on Computer Vision, 2016.
    25. 25)
      • 36. Yang, J., Reed, S., Yang, M.-H., et al: ‘Weakly-supervised disentangling with recurrent transformations for 3D view synthesis’. NIPS, 2015.
    26. 26)
      • 13. Yang, M., Gool, L.V., Zhang, L.: ‘Sparse variation dictionary learning for face recognition with a single training sample per person’. IEEE Int. Conf. on Computer Vision (ICCV), Sydney, NSW, 2013, pp. 689–696.
    27. 27)
      • 4. Wang, X., Tang, X.: ‘A unified framework for subspace face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (9), pp. 122–1228.
    28. 28)
      • 3. Guo, G., Li, S.Z., Chan, K.: ‘Face recognition by support vector machines’. Proc. of the IEEE Int. Conf. on Automatic Face and Gesture Recognition, March 2000, pp. 196–201.
    29. 29)
      • 21. Hayat, M., Bennamoun, M., An, S.: ‘Deep reconstruction models for image set classification’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (4), pp. 713–727.
    30. 30)
      • 1. Tan, X., Chen, S., Zhou, Z.-H., et al: ‘Face recognition from a single image per person: a survey’, Pattern Recognit., 2006, 39, (9), pp. 1725–1745.
    31. 31)
      • 31. http://ufldl.stanford.edu/wiki/index.php/Data_Preprocessing.
    32. 32)
      • 26. Martinez, A.M., Benavente, R.: ‘The AR face database’. CVC Technical Report #24, June 1998.
    33. 33)
      • 10. Lu, J., Zhou, X., Tan, Y.: ‘Discriminative transfer learning for single-sample face recognition’. Int. Conf. on Biometrics (ICB), Phuket, 2015, pp. 272–277.
    34. 34)
      • 9. Chen, C.-P., Chen, C.-S.: ‘Intrinsic illumination subspace for lighting insensitive face recognition’, IEEE Trans. Syst. Man Cybern. B, Cybern., 2012, 42, (2), pp. 422–433.
    35. 35)
      • 29. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: ‘Learning representations by back-propagating errors’, Nature, 1986, 23, (6088), pp. 533–536.
    36. 36)
      • 32. http://ufldl.stanford.edu/wiki/index.php/Whitening.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0322
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0322
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address